DETAILED ACTION
Allowable Subject Matter
Claims 5 and 6 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 8, and 9 are rejected under 35 U.S.C. 103 as being unpatentable over NAKAJIMA (Pub. No. US 2019/0278289 hereinafter “NAK”) in view of Wang et al. (Pub. No. US 2009/0309765).
Regarding claims 1, 8, and 9, NAK teaches an information processing apparatus (autonomous mobile apparatus) [Para. 26 “As shown in FIG. 4, the autonomous mobile apparatus 100 comprises, in addition to the feedback signal receivers 31 (31a, 31b), the drivers 32 (32a, 32b), the imager 33, and the charge connectors 35, a controller 10, a memory 20 and a communicator 34”] comprising: at least one memory storing instructions [fig. 4 and related description]; and at least one processor configured to execute the instructions [Para. 4 and related description] to: detect a plurality of new feature points (extracted feature points) from a first image (image data) [Para. 52 “In Step S211, its own location is estimated in the tracking procedure by the SLAM. This tracking procedure, first, extracts feature points from image data that are captured by the imager 33 and acquires, using the feature quantities, a correspondence between the extracted feature points and feature points for which the 3D coordinates are already estimated in a key frame included in the environment map (the estimation environment map)”]; specify, among the plurality of new feature points (extracted feature points), a corresponding feature point (corresponding feature points) corresponding to a known feature point (feature points for which the 3D coordinates are already estimated) associated with a three-dimensional position (3D coordinates) included in at least one management image (key frame) used for generating an environment map [Para. 30 “Here, a key frame is a frame that is used in the SLAM for estimating a three-dimensional (3D) location among images (frames) that are captured by the imager 33”; Para. 38 “The map creator 12 creates environment map data that comprise a set of key frame information and a set of MapPoint information shown in FIG. 5 by the SLAM using the image data that are captured by the imager 33 and writes the data in the map storage 21”; Para. 52 “In Step S211, its own location is estimated in the tracking procedure by the SLAM. This tracking procedure, first, extracts feature points from image data that are captured by the imager 33 and acquires, using the feature quantities, a correspondence between the extracted feature points and feature points for which the 3D coordinates are already estimated in a key frame included in the environment map (the estimation environment map)”; Para. 52 “If the number of feature points with the correspondence acquired (the corresponding feature points) is equal to or higher than a reference trackable number (for example, 10), the controller 10 can estimate its own location from the relationship between the 2D coordinates of the corresponding feature points in the image and the 3D coordinates within the environment map”]; estimate a position and a posture (posture (the location (3D coordinates) and the orientation)) of an imaging device (imager 33) that has captured the first image (image data), by using the corresponding feature point (corresponding feature points) [Para. 30 “Then, as shown in FIG. 5, the key frame information includes a 3D posture (a location (3D coordinates) and an orientation) within an environment map (in a three-dimensional space) of the imager 33 (the autonomous mobile apparatus 100) when the key frame is captured and information of multiple feature points that are included in the key frame”; Para. 39 “The own location estimator 13 estimates the posture (the location (3D coordinates) and the orientation) of the autonomous mobile apparatus 100 within the environment map by the SLAM using the image data that are captured by the imager 33 and the environment map data that are created by the map creator 12”; Para. 52 “If the number of feature points with the correspondence acquired (the corresponding feature points) is equal to or higher than a reference trackable number (for example, 10), the controller 10 can estimate its own location from the relationship between the 2D coordinates of the corresponding feature points in the image and the 3D coordinates within the environment map.”]; and
NAK also teaches new feature points (extracted feature points) to be detected from a target image (image data) that is a target for estimating the position and the posture (posture (the location (3D coordinates) and the orientation)) of the imaging device (imager 33) and the number of corresponding feature points (corresponding feature point) [Para. 39 “posture (the location (3D coordinates) and the orientation)”, “image data that are captured by the imager 33”; Para. 52 “extract feature points” and “number of corresponding feature points”].
However, NAK doesn’t explicitly teach change the number of new feature points to be detected from a target image according to the number of corresponding feature points.
Wang teaches changing the number (bring the total number back up to a desired level) of new feature points (feature points) to be detected from a target image (current image) according to the number of corresponding feature point (tracking points) [Para. 33].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify NAK’s SLAM tracking procedure by applying Wang’s count-triggered feature replenishment so that NAK’s detector obtains additional feature points from the target image (image data) when NAK’s number of corresponding feature points (corresponding feature points) is insufficient, while Wang’s current image (current image) and tracking points (tracking points) provide the analogous replenishment-image and count-control logic rather than replacing NAK’s map corresponding feature points. This modification improves NAK for estimating the position and posture of the imaging device while avoiding additional feature detection when the correspondence count is sufficient.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over NAKAJIMA (Pub. No. US 2019/0278289 hereinafter “NAK”) in view of Wang et al. (Pub. No. US 2009/0309765) further in view of Wu (Pub. No. US 2017/0309031).
Regarding claim 2, NAK teaches the number of corresponding feature points (corresponding feature points) is larger than a target number (reference trackable number) and the number of corresponding feature points (corresponding feature points) is smaller than the target number [Para. 52].
However, NAK in view of Wang doesn’t explicitly teach the claim limitations.
Wu teaches reducing the number of new feature points to be detected from the target image to a number smaller than a currently set number in a case where the number of corresponding feature points (tracked feature points) is larger than a target number (thresholds), and increase the number of new feature points to be detected from the target image to a number larger than the currently set number in a case where the number of corresponding feature points (tracked feature points) is smaller than the target number (threshold) [Para. 31, 32, 39, and 40].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify NAK in view of Wang’s feature point extraction logic by incorporating Wu’s threshold-controlled state machine based on tracked feature point so that NAK reduces new feature point detection when the corresponding point population is above the target and increases new feature point detection by adding new feature points. This modification improves NAK by avoiding unnecessary feature detection when sufficient correspondences are available while replenishing feature support when the correspondence count becomes inadequate for reliable position.
Claims 3 and 4 are rejected under 35 U.S.C. 103 as being unpatentable over NAKAJIMA (Pub. No. US 2019/0278289 hereinafter “NAK”) in view of Wang et al. (Pub. No. US 2009/0309765) further in view of CHANG et al. (Pub. No. US 2016/0110878).
Regarding claim 3, NAK teaches the corresponding feature point (corresponding feature points) and the three-dimensional position (3D coordinates) associated with the known feature point [Para. 52] and change the number of new feature points to be detected from the target image that is the target for estimating the position and the posture of the imaging device according to the number of corresponding feature points (corresponding feature points) [Para. 52].
However, NAK in view of Wang doesn’t explicitly teach the rest of claim limitations.
CHANG teaches the corresponding feature point specify a high-accuracy feature point of which a distance between a projection point obtained by projecting, on the first image, the three-dimensional position associated with the known feature point and the corresponding feature point is shorter than a predetermined distance (predetermined tolerance) [Para. 44],
and a low-accuracy feature point of which the distance between the projection points and the corresponding feature point is longer than the predetermined distance, and change the number of new feature points to be detected from the target image that is the target for estimating the position and the posture of the imaging device, according to the number of high-accuracy feature points (new feature points) [Para. 31 and 39].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify NAK in view of Wang’s SLAM correspondence processing by incorporating Chang’s inlier determination using three-dimensional position and predetermined tolerance to identify geometrical reliable corresponding feature points. This modification preserves position and posture estimation accuracy while reducing unnecessary processing.
Regarding claim 4, NAK teaches the number of corresponding feature points (corresponding feature points) is compared with a target number (reference trackable number) [Para. 52].
However, NAK in view of Wang doesn’t explicitly teach the rest of claim limitations.
Chang teaches having high accuracy feature points [Para. 43 and 44].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify NAK in view of Wang’s SLAM correspondence processing by incorporating Chang’s inlier determination using three-dimensional position and predetermined tolerance to identify geometrical reliable corresponding feature points. This modification preserves position and posture estimation accuracy while reducing unnecessary processing.
NAK in view of Wang further in view of Chang doesn’t explicitly teach the remaining claim limitations.
However, Wu teaches reducing the number of new feature points to be detected when the feature point populations is above the threshold and increases the number of new features points (new feature points) when the feature point population is below thresholds (thresholds) [Para. 32, 39, and 40].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify NAK in view of Wang further in view of Chang’s feature point extraction logic by incorporating Wu’s threshold-controlled state machine based on tracked feature point so that NAK reduces new feature point detection when the corresponding point population is above the target and increases new feature point detection by adding new feature points. This modification improves NAK by avoiding unnecessary feature detection when sufficient correspondences are available while replenishing feature support when the correspondence count becomes inadequate for reliable position.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over NAKAJIMA (Pub. No. US 2019/0278289 hereinafter “NAK”) in view of Wang et al. (Pub. No. US 2009/0309765) further in view of Park et al. (Pub No. US 2012/0162450).
Regarding claim 7, NAK in view of Wang doesn’t explicitly teach the claim limitations.
However, Park teaches wherein the at least one processor is further configured to execute the instructions to change the number of new feature points to be detected from the target image in a range between a maximum value (maximum number of features points) and a minimum value (minimum number (min_features)) of the number of new feature points to be detected from the target image [Para. 52 and 54].
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify NAK in view of Wang’s feature point-based localization process, by incorporating Park’s minimum number (minimum number (min_features)) and maximum number constraints so that the number of new feature points detected from each target image is changed only within a bounded range. This modification improves NAK by preventing too few feature points for reliable position and posture estimation while also preventing excessive feature-point detection that would increase processing load.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SOLOMON G BEZUAYEHU whose telephone number is (571)270-7452. The examiner can normally be reached on Monday-Friday 10 AM-7 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, O’Neal Mistry can be reached on 313-446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-0101 (IN USA OR CANADA) or 571-272-1000.
/SOLOMON G BEZUAYEHU/ Primary Examiner, Art Unit 2666
Prosecution Insights